DocumentCode
296120
Title
Neural networks trained for associative memory
Author
Xiaohong, Bao ; Yingmin, Jia
Author_Institution
Seventh Res. Div., Beijing Univ. of Aeronaut. & Astronaut., China
Volume
4
fYear
1995
fDate
Nov/Dec 1995
Firstpage
1783
Abstract
This paper presents a learning method for designing associative memories using recurrent feedforward neural networks (RFNNs) which can also be implemented by fully interconnected recurrent neural networks (FIRNNs) attached on a linear output layer. This technique guarantees that desired memories are stored and are attractive over the prescribed domains. The learning method can be traced back to the BP algorithm
Keywords
backpropagation; content-addressable storage; feedforward neural nets; recurrent neural nets; associative memory; fully interconnected recurrent neural networks; learning method; linear output layer; recurrent feedforward neural networks; Associative memory; Bismuth; Design methodology; Differential equations; Feedforward neural networks; Guidelines; Learning systems; Neural networks; Recurrent neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location
Perth, WA
Print_ISBN
0-7803-2768-3
Type
conf
DOI
10.1109/ICNN.1995.488891
Filename
488891
Link To Document